MediaCrawler/media_platform/kuaishou/client.py

# -*- coding: utf-8 -*-
import asyncio
import json
from urllib.parse import urlencode
from typing import Dict, Optional

import httpx
from playwright.async_api import BrowserContext, Page

from tools import utils

from .graphql import KuaiShouGraphQL
from .exception import DataFetchError, IPBlockError


class KuaiShouClient:
    def __init__(
            self,
            timeout=10,
            proxies=None,
            *,
            headers: Dict[str, str],
            playwright_page: Page,
            cookie_dict: Dict[str, str],
    ):
        self.proxies = proxies
        self.timeout = timeout
        self.headers = headers
        self._host = "https://www.kuaishou.com/graphql"
        self.playwright_page = playwright_page
        self.cookie_dict = cookie_dict
        self.graphql = KuaiShouGraphQL()

    async def request(self, method, url, **kwargs) -> Dict:
        async with httpx.AsyncClient(proxies=self.proxies) as client:
            response = await client.request(
                method, url, timeout=self.timeout,
                **kwargs
            )
        data: Dict = response.json()
        if data.get("errors"):
            raise DataFetchError(data.get("errors", "unkonw error"))
        else:
            return data.get("data", {})

    async def get(self, uri: str, params=None) -> Dict:
        final_uri = uri
        if isinstance(params, dict):
            final_uri = (f"{uri}?"
                         f"{urlencode(params)}")
        return await self.request(method="GET", url=f"{self._host}{final_uri}", headers=self.headers)

    async def post(self, uri: str, data: dict) -> Dict:
        json_str = json.dumps(data, separators=(',', ':'), ensure_ascii=False)
        return await self.request(method="POST", url=f"{self._host}{uri}",
                                  data=json_str, headers=self.headers)

    async def pong(self) -> bool:
        """get a note to check if login state is ok"""
        utils.logger.info("Begin pong kuaishou...")
        ping_flag = False
        try:
            pass
        except Exception as e:
            utils.logger.error(f"Pong kuaishou failed: {e}, and try to login again...")
            ping_flag = False
        return ping_flag

    async def update_cookies(self, browser_context: BrowserContext):
        cookie_str, cookie_dict = utils.convert_cookies(await browser_context.cookies())
        self.headers["Cookie"] = cookie_str
        self.cookie_dict = cookie_dict

    async def search_info_by_keyword(self, keyword: str, pcursor: str):
        """
        KuaiShou web search api
        :param keyword: search keyword
        :param pcursor: limite page curson
        :return:
        """
        post_data = {
            "operationName": "visionSearchPhoto",
            "variables": {
                "keyword": keyword,
                "pcursor": pcursor,
                "page": "search"
            },
            "query": self.graphql.get("search_query")
        }
        return await self.post("", post_data)


    async def get_video_info(self, photo_id: str) -> Dict:
        """
        Kuaishou web video detail api
        :param photo_id:
        :return:
        """
        post_data = {
            "operationName": "visionVideoDetail",
            "variables": {
                "photoId": photo_id,
                "page": "search"
            },
            "query": self.graphql.get("video_detail")
        }
        return await self.post("", post_data)